Accepted File Types in CreateAI Builder

CreateAI Builder supports a wide range of file types for uploading into your project’s Knowledge Base. This guide provides the full list of accepted file formats.

Faith Timoh Abang

September 8, 2025

📷 Images

.jpg, .jpeg
.png
.webp
.gif

🎵 Audio

.mp3
.wav
.mpeg
.m4a

🎥 Video

.mp4
.webm

📄 Documents & Text

.csv
.eml, .msg (email formats)
.epub (eBook)
.xlsx (Excel)
.htm, .html (web pages)
.md (Markdown)
.org (Org-mode files)
.odt (OpenDocument Text)
.pdf
.txt, .text, .log (plain text and logs)
.pptx (PowerPoint)
.rst (reStructuredText)
.rtf (Rich Text Format)
.tsv (tab-separated values)
.docx (Word)
.xml
.json
.web (web archive)

💻 Code Files

.js (JavaScript)
.py (Python)
.java (Java)
.cpp, .cxx, .cc, .c (C/C++)
.cs (C#)
.php
.rb (Ruby)
.swift
.ts (TypeScript)
.go (Go)

Notes

Files must not exceed the maximum upload size set for your project.
Only the file types listed above are supported. Unsupported formats may fail to upload.

Sensitive data rules apply, always check with the ASU Data Classification Tool before uploading.

Keep Reading

Falling words in various depths of field resembling AI code

Breakdown of RAG Model Parameters, Settings and Their Impact

Kofi Wood

January 1, 2025

Retrieval-Augmented Generation (RAG) is an advanced approach in natural language processing that integrates information retrieval and generative language modeling. Unlike traditional language models that generate responses solely based on their pre-trained knowledge, RAG combines retrieval mechanisms with generative models to enhance the relevance and accuracy of its responses. This hybrid framework works by first retrieving relevant documents or information from a predefined knowledge base (e.g., databases, documents, or PDFs) and then using a generative model (such as a transformer-based model) to synthesize a response that incorporates the retrieved context.